Some applications of soft computing methods in system modelling and control

Abstract

The paper deals with the application of fuzzy systems, artificial neural networks (neural systems) and genetic algorithms to solve modelling and control problems in system engineering. The first part of the paper deals with the design of classical PID and fuzzy PID-type controllers for nonlinear systems with (approximately) known dynamic model. The optimal controllers are designed based on genetic algorithms. The second part considers the neural control of a SCARA robot. The third part deals with the fuzzy control of a special class of MIMO nonlinear systems and generalizes the method of Wang (1994) for such systems.